Vahid Balali

Integration of ELECTRE III and PROMETHEE II Decision-Making Methods with an Interval Approach: Application in Selection of Appropriate Structural Systems

AbstractThe problem of selection or ranking of alternatives based on multiple criteria is not an easy problem, neither economically nor mathematically. The recent advancements in various structural systems have made the selection of the appropriate structural system for a specific project a challenging decision-making process. This process involves different economic and technical criteria representing the availability of experienced technicians and engineers and necessary machinery and construction materials. Economic life cycle, environmental protection related issues, safety of the project site, and vulnerability to natural disasters such as earthquakes are also issues related to the country and location in which the construction project takes place, and they should also be addressed in the decision-making process. In this paper, a new algorithm combining two well-known multicriteria decision-making (MCDM) techniques, namely, elimination and choice expressing the reality III (ELECTRE III) and preferenc...

Evaluation of Multiclass Traffic Sign Detection and Classification Methods for U.S. Roadway Asset Inventory Management

AbstractFrequent analysis and updating the condition of traffic signs and mile markers are among the most important aspects of a highway asset management system. Today’s practices mainly involve manual data collection and analysis, which have to be done for millions of miles of roads and the practice needs to be repeated regularly. While significant progress has been made on improving the data collection practice by leveraging video streams collected from car-mounted cameras, the analysis has primarily remained a manual and labor-intensive process. Automating the analysis from the collected videos is also challenging due to the interclass variability of traffic signs, expected changes in illumination, occlusion, sign position, and orientation. To address these challenges, this paper presents and evaluates the performance of three computer vision algorithms for detection and classification of traffic signs in presence of cluttered backgrounds and static and dynamic occlusions. The task particularly focuses...

Video-Based Detection and Classification of US Traffic Signs and Mile Markers using Color Candidate Extraction and Feature-Based Recognition

Traffic sign and mile-marker detection and classification are among the important components of highway asset management systems. The significant number of these high-quantity and low-cost assets in US highways can negatively impact the quality of any manual data collection and analysis. To address these challenges, this paper presents an efficient pipeline for video-based detection and classification of traffic signs and mile-markers based on color and shape criteria. Candidate extraction is based on finding the optimum red, green, blue (RGB) thresholds which yield high detection rates (very low false-negatives) while keeping the number of false-positives in check. The connected components from a thresholded image are extracted next. The authors use sliding windows, Haar-like features, and the AdaBoost learning method to classify the detected assets. Experimental results with an average classification accuracy of 79.30% on actual data collected from US-460 highway show the promise of the proposed method for reducing the time and effort required for developing traffic road asset inventories.

Selection of Appropriate Material, Construction Technique, and Structural System of Bridges by Use of Multicriteria Decision-Making Method

Decision makers in the transportation industry search for a systematic approach to select an appropriate structural system, construction method, and material for bridges. Simple mathematical methodologies are needed to consider different stakeholders’ perspectives. With criteria that occur simultaneously in selecting appropriate material, construction technique, and structural system of bridges, invalid and unexpected results may occur from such complexity. The decision-making process is usually done subjectively by designers and requires much data and extensive experience in bridge design. To address these challenges and assume all substantial criteria within the framework, the PROMETHEE (Preference Ranking Organization Method for Enrichment Evaluation) multi-criteria decision-making method is used. It is not sensitive to the number and definition of the criteria. The PROMETHEE method is based on the pairwise comparison between alternatives for constructing an outranking relationship to show the degree of dominance of one alternative over another. A case study of the Kashkhan Bridge in Iran is presented to demonstrate implementation of the PROMETHEE method and show how such a decision-making methodology can assist experts in making informed decisions based on a set of comprehensive criteria in the conceptual design stage. Some novel and effective criteria in this study are combined and synthesized to select the appropriate superstructure. Criteria weights and preference and indifference thresholds are collected through questionnaires filled out by bridge experts. Results of the case study show that the most appropriate system for the Kashkhan Bridge is the box girder system with the balanced cantilever method and posttensioned concrete material.

Image-based retro-reflectivity measurement of traffic signs in day time

Display Omitted A vision method that remotely measures traffic sign retro-reflectivity in daytime.The method simulates nighttime visibility from images taken during daytime.The impact of time of day and distance on measurements are studied.The method with accuracy of 95.24% is cheaper, faster and safer than current practice.The method satisfies FHWA measurement requirements on accuracy and granularity. The visibility of a traffic sign at night depends on its retro-reflectivity, a property that needs to be frequently monitored to ensure transportation safety. In the U.S., Federal Highway Administration (FHWA) maintains regulations to ensure minimum retro-reflectivity levels. Current measurement techniques either (a) use vehicle mounted device during the night, or (b) use manual handheld devices during the day. The former is expensive due to nighttime labor cost. The latter is time-consuming and unsafe. To address these limitations, this paper presents a computer vision-based technique to measure retro-reflectivity during daytime using a vehicle mounted device. The presented algorithms simulate nighttime visibility of traffic signs from images taken during daytime and measure their retro-reflectivity. The technique is faster, cheaper, and safer as it neither requires nighttime operation nor requires manual sign inspection. It also satisfies FHWA measurement guidelines both in terms of granularity and accuracy. The performance of the presented technique is evaluated under various testing conditions. The results are promising and demonstrate a strong potential in lowering inspection cost and improving safety in practical applications on retro-reflectivity measurement.

Prioritizing Sustainable Transport Projects through Multicriteria Group Decision Making: Case Study of Tianjin Binhai New Area, China

AbstractIt is challenging to devise a group decision-making process that supports compromise solutions reflecting diverse stakeholders’ preferences about multiple criteria. This study illustrates how the combination of multicriteria decision analysis and a group decision-making technique can be used to arrive at solutions that are mutually acceptable to multiple stakeholders when selecting sustainable transport projects. The proposed methodology, in which the collective preference is determined based on the aggregation of individual preferences from all stakeholders, is illustrated through a case study of the prioritization of nine prospective transport projects affecting three stakeholder groups (decision-makers, project designers, and system users) in Tianjin Binhai New Area, China. Specifically, the various projects were evaluated for their probable sustainability performance according to 14 criteria. The results show that the proposed methodology can enable transportation managers to achieve an accept...

Recognition and 3D Localization of Traffic Signs via Image-Based Point Cloud Models

Recently, the US Departments of Transportation have pro-actively looked into videotaping roadway assets. Using inspection vehicles equipped with high resolution cameras, accurate information on location and condition of high quantity and low cost roadway assets are being collected. While many efforts have focused on streamlining the data collection, the analysis is still manual and involves painstaking and subjective processes. Their high cost has also limited the scope of the visual assessments to critical roadways only. To address current limitations, this paper presents an automated method to detect, classify, and accurately localize traffic signs in three-dimensional (3D) using existing visual data. Using a discriminative learning method based on Histograms of Oriented Gradients and Color, traffic signs are detected and classified into multiple categories. Then, a Structure from Motion procedure creates a 3D point cloud from the street level images, and triangulates the location of the detected signs in 3D. The experimental results show that the method reliably detects and localizes traffic signs and demonstrate a strong potential in improving assessments and lowering cost in practical applications.

Erratum for “Evaluation of Multiclass Traffic Sign Detection and Classification Methods for U.S. Roadway Asset Inventory Management” by Vahid Balali and Mani Golparvar-Fard

“ : : :The detection and classification methods are as shown in Fig. 2 are (1) Haar-like features with Adaboost classifiers, (2) histogram of oriented gradients with support vector machine classifiers, and (3) a new variant of HOG features where histogram of local color distributions are formed and concatenated with the HOG descriptors (Memarzadeh et al. 2013) to leverage both shape and color information for multiple traffic sign category with one-versus-all SVM classifiers.”